Paper published in a journal (Scientific congresses, symposiums and conference proceedings)
MetaTPTrans: A Meta Learning Approach for Multilingual Code Representation Learning
PIAN, Weiguo; Peng, Hanyu; TANG, Xunzhu et al.
2023In Proceedings of the AAAI Conference on Artificial Intelligence, 37 (4), p. 5239-5247
Peer reviewed
 

Files


Full Text
2023-AAAI-MetaTPTrans.pdf
Author preprint (2.52 MB)
Download

All documents in ORBilu are protected by a user license.

Send to



Details



Abstract :
[en] Representation learning of source code is essential for applying machine learning to software engineering tasks. Learning code representation from a multilingual source code dataset has been shown to be more effective than learning from single-language datasets separately, since more training data from multilingual dataset improves the model's ability to extract language-agnostic information from source code. However, existing multilingual training overlooks the language-specific information which is crucial for modeling source code across different programming languages, while only focusing on learning a unified model with shared parameters among different languages for language-agnostic information modeling. To address this problem, we propose MetaTPTrans, a meta learning approach for multilingual code representation learning. MetaTPTrans generates different parameters for the feature extractor according to the specific programming language type of the input code snippet, enabling the model to learn both language-agnostic and language-specific information with dynamic parameters in the feature extractor. We conduct experiments on the code summarization and code completion tasks to verify the effectiveness of our approach. The results demonstrate the superiority of our approach with significant improvements on state-of-the-art baselines.
Disciplines :
Computer science
Author, co-author :
PIAN, Weiguo ;  University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > TruX
Peng, Hanyu
TANG, Xunzhu ;  University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > TruX
SUN, Tiezhu  ;  University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > TruX
TIAN, Haoye ;  University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > TruX
Habib, Andrew
KLEIN, Jacques ;  University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > TruX
BISSYANDE, Tegawendé François d Assise  ;  University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > TruX
External co-authors :
yes
Language :
English
Title :
MetaTPTrans: A Meta Learning Approach for Multilingual Code Representation Learning
Publication date :
February 2023
Event name :
Thirty-Seventh AAAI Conference on Artificial Intelligence
Event date :
February 2023
Audience :
International
Journal title :
Proceedings of the AAAI Conference on Artificial Intelligence
ISSN :
2374-3468
eISSN :
2159-5399
Publisher :
Association for the Advancement of Artificial Intelligence (AAAI)
Volume :
37
Issue :
4
Pages :
5239-5247
Peer reviewed :
Peer reviewed
Available on ORBilu :
since 28 December 2023

Statistics


Number of views
18 (2 by Unilu)
Number of downloads
3 (0 by Unilu)

Scopus citations®
 
1
Scopus citations®
without self-citations
1

Bibliography


Similar publications



Contact ORBilu